MISTRAL: a Statistical Machine Translation Decoder for Speech Recognition Lattices

Alexandre Patry, Philippe Langlais

[How to correct problems with metadata yourself]

Abstract
This paper presents MISTRAL, an open source statistical machine translation decoder dedicated to spoken language translation. While typical machine translation systems take a written text as input, MISTRAL translates word lattices produced by automatic speech recognition systems. The lattices are translated in two passes using a phrase-based model. Our experiments reveal an improvement in BLEU when translating lattices instead of sentences returned by a speech recognition system.
Anthology ID:
L08-1485
Volume:
Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08)
Month:
May
Year:
2008
Address:
Marrakech, Morocco
Editors:
Nicoletta Calzolari, Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odijk, Stelios Piperidis, Daniel Tapias
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
Language:
URL:
http://www.lrec-conf.org/proceedings/lrec2008/pdf/293_paper.pdf
DOI:
Bibkey:
Cite (ACL):
Alexandre Patry and Philippe Langlais. 2008. MISTRAL: a Statistical Machine Translation Decoder for Speech Recognition Lattices. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).
Cite (Informal):
MISTRAL: a Statistical Machine Translation Decoder for Speech Recognition Lattices (Patry & Langlais, LREC 2008)
Copy Citation:
PDF:
http://www.lrec-conf.org/proceedings/lrec2008/pdf/293_paper.pdf
PDF Search